Comments on new conditions for global stability of neural networks with application to linear and quadratic programming problems

Document Type


Publication Date



This letter makes the following comments on the results about global stability of neural networks presented in Forti and Tesi in the above paper: 1) the assumption of all neuron activation functions to vanish at the origin, which is utilized in the proof of the result (see the above paper [p. 357, Section III, Th. 3]) implying the existence and uniqueness of the network equilibrium point, can be actually omitted; 2) in the infinite sector case, the result of global asymptotic stability (GAS) (see the above paper [p. 359, Section IV, Th. 5]) remains true with respect to the class of increasing (not necessarily strictly) activations, as in the finite sector case. Consequently, a result about absolute stability (ABST) of neural networks, which can represent a generalization of the existing related ones, is also obtained. © 1997 IEEE.

Publication Source (Journal or Book title)

IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications

First Page


Last Page


This document is currently not available here.